Researchers Create AI that Reviews Products

In 2020, the computer science team of Alan Riddell, Dan Rockmore, and Keith Carlson set out to create a computer code to write product reviews. However, they struggled with a practical question.

‘Getting the code to write reviews was only the first part of the challenge,’ says Carlson, a doctoral research fellow at the Tuck School of Business. ‘The remaining challenge was figuring out how and where it could be used.’

The objective of the team was to see if artificial intelligence could be made to write ‘synthesis reviews’ about vast product classes.

They mainly focused on reviews of alcoholic beverages because there was extensive material to work with. The vocabulary used in the description of the products was also narrow enough to make it open to the methods of AI systems and natural language processing tools.

Despite the code’s inability to taste the products, the team found that it could complete the tasks after training the algorithm on thousands of published reviews.

One result read ‘This is a sound Cabernet. It’s very dry and a little thin in blackberry fruit, which accentuates the acidity and tannins. Drink up.’

The team then wondered ‘Who else would care about this?’ Rockmore said, ‘I was sure that this work could be interesting to a wider audience.’

Praveen Kopalle, Professor of Management at Tuck School of Business, recalled thinking ‘Brilliant’, when she first reviewed the technical study. She knew the research was important and could ‘disrupt’ the online review industry.

‘The paper has a lot of marketing applications, particularly in the context of online reviews where we can create reviews or descriptions of products when they may not already exist,’ said Kopalle. ‘In fact, we can even think about summarizing review for products and services as well.’

Prasad Vana, Assistant Professor of Business Administration at Tuck, was added to complete the team. Vana reorganized the review-writing code into a market-friendly tool to aid professional reviewers, consumers and marketers.

The research was published in International Journal of Research in Marketing.

‘Using artificial intelligence to write and synthesize reviews can create efficiencies on both sides of the marketplace,’ said Vana. ‘The hope is that AI can benefit reviewers facing larger writing workloads and consumers who have to sort through so much content about products.’

‘It’s interesting to imagine how this could benefit restaurants that cannot afford sommeliers or independent sellers on online platforms who may sell hundreds of products,’ said Vana.

By Marvellous Iwendi.

Source: Darthmouth Edu